How to Use the Lambda Labs (GPU Cloud) MCP in Google ADK

Q: How can I use Google ADK to manage my Lambda Labs (GPU Cloud) budget?

Build an agent that periodically runs listinstances to check for idle machines. Based on your rules, it can then use terminateinstances to shut down anything that's wasting money.

Q: Does this MCP server work with Gemini's long context for Lambda Labs (GPU Cloud) tasks?

Yes, it's a great fit. You can feed the output of listinstancetypes and listinstances into the Gemini model, and it can reason over your entire Lambda Labs (GPU Cloud) estate to make complex decisions.

Q: Is it possible to filter which tools from this MCP server my Google ADK agent can use?

Yes, the McpToolset in Google ADK has a toolnames filter. You could, for example, create a 'monitor-only' agent that can only call listinstances and getinstance.

Connect your Google ADK agents to your Lambda Labs GPU fleet and run training jobs on data from your Google Cloud environment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lambda Labs (GPU Cloud) MCP to Google ADK

Create your Vinkius account to connect Lambda Labs (GPU Cloud) to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Lambda Labs (GPU Cloud) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Spin Up and Tear Down GPU Nodes

The `launch_instance` and `terminate_instances` tools let your agent control the full lifecycle of your GPU resources. A Gemini-powered agent can reason about your workload, pick an instance from `list_instance_types`, and spin it up for a training run. When the job is done, the agent calls `terminate_instances` to stop the billing instantly. Because Google ADK is built for long-running tasks, you can build an agent that manages a whole fleet over days or weeks, optimizing for cost. This is where an MCP toolset is powerful.

Bridge Google Cloud and Lambda Labs

Use `list_instances` and `get_instance` to feed the status of your Lambda Labs machines directly into your Google Cloud operations. An agent can pull instance IPs and statuses, then update a BigQuery table or trigger a Cloud Function. This turns Lambda Labs into an extension of your GCP environment. Your agent acts as the bridge, using its long context window to manage complex, multi-step workflows that span both platforms. This MCP server is the key to that connection.

Control Filesystems and SSH Access

The `list_filesystems` tool allows your agent to see available persistent storage before it even launches an instance. It can make sure the right dataset is available for the job. Your agent can also use `list_ssh_keys` to check for the required credentials. This prevents provisioning an instance that your automated systems can't access, which is critical for enterprise-grade automation. This MCP toolset gives your agent the visibility it needs.

Setup guide

Set up Lambda Labs (GPU Cloud) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Lambda Labs (GPU Cloud) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Lambda Labs (GPU Cloud)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Lambda Labs (GPU Cloud) tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Lambda Labs. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Lambda Labs (GPU Cloud) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Lambda Labs (GPU Cloud) MCP in Google ADK

Build an agent that periodically runs `list_instances` to check for idle machines. Based on your rules, it can then use `terminate_instances` to shut down anything that's wasting money.

Yes, it's a great fit. You can feed the output of `list_instance_types` and `list_instances` into the Gemini model, and it can reason over your entire Lambda Labs (GPU Cloud) estate to make complex decisions.

Absolutely. Your agent's logic should include error handling for the `launch_instance` call. If a specific GPU type isn't available, it can parse the error and try a different one.

Yes, the `McpToolset` in Google ADK has a `tool_names` filter. You could, for example, create a 'monitor-only' agent that can only call `list_instances` and `get_instance`.

The server only processes infrastructure metadata from Lambda Labs (GPU Cloud), like instance IDs, specs, and SSH public keys. It never touches your training data. All tool access can be logged and audited using Google Cloud's native tools, fitting into your existing security posture.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript